Professional Documents
Culture Documents
I. INTRODUCTION
Face detection is used in biometrics, often as a part of (or
together with) a facial recognition system. It is also used in
video surveillance, human computer interface and image
database management. Some recent digital cameras use face
detection for auto focus. Face detection can be applied for a
wide variety of problems like image and film processing,
human-computer interaction, criminal identification etc. This
has motivated researchers to develop computational models to
identify the faces, which are relatively simple and easy to
implement. Our goal is to implement the model for a set of
training images and find a mean image of all the images so as
to compute the difference between it and the input image for
proper detection.
Facial recognition is a form of computer vision that uses
faces to identify a person or verify a persons claimed
identity. A facial recognition device is one that views an
image or video of a person and compares it to one that is in
the database. It does this by comparing structure, shape and
23
ISSN:2348 9510
International Journal Of Core Engineering & Management(IJCEM)
Volume 1, Issue 2, May 2014
then used to identify distinctive features on the face, such as
the contour of eye sockets, nose and chin.
The advantages of 3-D facial recognition are that it is not
affected by changes in lighting, and it can identify a face from
a variety of angles, including profile view.
Another new technique in facial recognition uses the visual
details of the skin, as captured in standard digital or scanned
images. This technique is called skin texture analysis, turns
the unique lines, patterns, and spots apparent in a person's skin
into a mathematical space. Preliminary tests have shown that
using skin texture analysis in facial recognition can increase
performance in identification by 20 to 25 percent.
Regardless of specific method used, the facial recognition is
accomplished in a five step process(Step 1) Acquiring the Image of an Individuals Face
2 ways to acquire image
1) Digitally scan an existing photograph
2) Acquire a live picture of a subject
(Step 2) Locate Image of Face
MATLAB (image processing toolbox)is used to locate the
image that has been used.
(Step 3)Analysis of Facial Image
-software measures face according to is peaks and valleys
(nodal points)
-nodal points are used to make a face print
1. Eigenfaces Initialization
Acquire an initial set of face images (the training set)
2. Eigenfaces Algorithm
Calculate the Eigen faces from the training set, keeping only
the M images that correspond to the highest Eigen values.
These M images define the face space. As new faces are
experienced, the Eigen faces can be updated or recalculated
3. Calculate the corresponding distribution in M-dimensional
weight space for each known individual, by projecting their
face images onto the face space.
(Step 4) Comparison
-the face print created by the software is compared to all face
prints the system has stored in its database.
(Step 5)-Match Or No Match
-software decides whether or not any comparisons from step 4
are close enough to declare a possible match
FACE RECOGNITION TECHNOLOGY WITH EIGEN
VALUES
Insert data
base image
Training
set
Give path
24
ISSN:2348 9510
International Journal Of Core Engineering & Management(IJCEM)
Volume 1, Issue 2, May 2014
Normalized
the training set
Taking
mean image
Getting
eigen faces
Giving
input
image
STEPS
1. The first step is to obtain a set S with M face images. Each
image is transformed into a vector of size N and placed into
the set.
2. After you have obtained your set, you will obtain the mean
image
3. Then you will find the difference between the input
image and the mean image
4. Next we seek a set of M ortho normal vectors, un, which
best describes the distribution of the data. The kth vector, uk, is
chosen such that is a maximum, subject to
Note: uk and k are the eigenvectors and eigenvalues of
the covariance matrix C
We obtain the covariance matrix C in the following manner
5. AT
6. Now we have to find the eigenvectors, vl, ul
2) VERIFICATION
-answer the question Is this X?
-accomplished by the system performing a one-to-one
search
BENEFITS
The benefits of facial recognition are that it is not intrusive,
can be done from a distance even without the user being
aware they are being scanned. (i.e.: bank or government
office)
What sets apart facial recognition from other biometric
techniques is that it can be used for surveillance purposes; as
in searching for wanted criminals, suspected terrorists, and
missing children. Facial recognition can be done from far
away so with no contact with the subject so they are unaware
they are being scanned.
Facial recognition is most beneficial to use for facial
authentication than for identification purposes, as it is too easy
RECOGNITION PROCEDURE
for someone to alter their face, features with a disguise or
1. A new face is transformed into its Eigen face components.
mask, etc. Environment is also a consideration as well as
First we compare our input image with our mean image and
subject motion and focus on the camera.
multiply their difference with each eigenvector of the L matrix. Facial recognition, when used in combination with another
Each value would represent a weight and would be saved on a
biometric method, can improve verification and identification
vector .
results dramatically.
2. We now determine which face class provides the best
description for the input image. This is done by minimizing
the Euclidean distance
3. The input face is considered to belong to a class if k is
bellow an established threshold . Then the face image is
considered to be a known face. If the difference is above the
given threshold, but bellow a second threshold, the image can
APPLICATION DOMAIN
As one of the most successful applications of image analysis
and understanding, face recognition has recently gained
significant attention image analysis and understanding face
especially during the past several years. There are at least two
reasons for such a trend: the first is the wide range
of commercial and law enforcement applications and the
second is the availability of feasible technologies after 35
25
ISSN:2348 9510
International Journal Of Core Engineering & Management(IJCEM)
Volume 1, Issue 2, May 2014
years of research. Moreover recent significant advances in
multimedia processing have also helped to advance the
applications of face recognition technology. Among the
diverse contents of multimedia face objects are particularly
important for e.g.- database software capable of searching for
ace objects or a particular face object is very useful.
Another example is a security system that is able to
automatically track human objects and report their
IDs.Though tracking and recognizing face objects is a routine
task for humans building such system is still an active
research. Among many proposed face recognition
Schemes image based approaches are possibly the most
promising ones. However the 2D images/patterns of 3D face
objects can dramatically change due to lighting and viewing
variations. Hence, illumination and pose problems present
significant
Obstacles for wide applications of this type of approaches. In
this we review existing methods extensively. And then we
propose using a generic 3D model to enhance existing system.
More specifically we use the 3D model to synthesize the socalled prototype image from a given image acquired under
different lighting and viewing condition. The advantages of
this approach are computational simplicity and system
robustness which are essential for any real applications.
REFERENCES
[1] http://www.face-rec.org/databases/
[2] Matthew A. Turk and Alex P. Pentland. Face
recognition using eigenfaces.
[3] www.mathworks.com
[4] :
http://www.intechopen.com/books/show/title/face_
recognition
26